Renormalization Group Flow Matching for Scalable Local Generative Modeling
cs.LG, cond-mat.stat-mech
Submitted: 2026-08-24
Updated: 2026-08-24
Code: https://github.com/kantamasuki/Local_RGFM
Terminology
Sources
- FourierFlow: Frequency-aware Flow Matching for Generative Turbulence Modeling
- Physics-Constrained Diffusion Model for Synthesis of 3D Turbulent Data
- Diffusion Models for Sampling Near Criticality in Lattice Field Theories
- Learning and Generating Mixed States Prepared by Shallow Channel Circuits
- Local Diffusion Models and Phases of Data Distributions
- Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models
- Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile
- GUD: Generation with Unified Diffusion
- Generative diffusion model with inverse renormalization group flows
- Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
- Deep learning and the renormalization group
- An exact mapping between the Variational Renormalization Group and Deep Learning
- Generative sampling with physics-informed kernels
- Solving Functional Renormalization Group Equations with Neural Networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks